NAACL
2010
13 years 2 months ago
2010
We present a method for disambiguating syntactic subjects from syntactic objects (a frequent ambiguity) in German sentences taken from an English-German bitext. We exploit the fac...
NAACL
2010
13 years 2 months ago
2010
Extraction of entities from ad creatives is an important problem that can benefit many computational advertising tasks. Supervised and semi-supervised solutions rely on labeled da...
NAACL
2010
13 years 2 months ago
2010
We consider the problem of predicting a movie's opening weekend revenue. Previous work on this problem has used metadata about a movie--e.g., its genre, MPAA rating, and cast...
NAACL
2010
13 years 2 months ago
2010
Automatically finding email messages that contain requests for action can provide valuable assistance to users who otherwise struggle to give appropriate attention to the actionab...
NAACL
2010
13 years 2 months ago
2010
We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. In particular, each component mul...
NAACL
2010
13 years 2 months ago
2010
We present Quantized Contour Modeling (QCM), a Bayesian approach to the classification of acoustic contours. We evaluate the performance of this technique in the classification of...
NAACL
2010
13 years 2 months ago
2010
We describe a Bayesian inference algorithm that can be used to train any cascade of weighted finite-state transducers on end-toend data. We also investigate the problem of automat...
NAACL
2010
13 years 2 months ago
2010
We describe a utility evaluation to determine whether cross-document information extraction (IE) techniques measurably improve user performance in news summary writing. Two groups...
NAACL
2010
13 years 2 months ago
2010
In this work, we try a hybrid methodology for language modeling where both morphological decomposition and factored language modeling (FLM) are exploited to deal with the complex ...
NAACL
2010
13 years 2 months ago
2010
This paper analyzes the topic identification stage of single-document automatic text summarization across four different domains, consisting of newswire, literary, scientific and ...